Join the Fabric Partner Community for this Week's Fabric Engineering Connection calls!
Are you a Microsoft partner that is interested in data and analytics? Be sure to join us for the next Fabric Engineering Connection calls! 🎉 Sujata Narayana will be sharing a recap of Power BI announcements from FabCon Europe, followed by the latest updates on AI Functions from Virginia Roman. The Americas & EMEA call will take place Wednesday, October 15, from 8-9 am PT and the APAC call is Thursday, October 16, from 1-2 am UTC/Wednesday, October 15, from 5-6 pm PT. This is your opportunity to learn more, ask questions, and provide feedback. To join the call, you must be a member of the Fabric Partner Community Teams channel. To join, complete the participation form at https://aka.ms/JoinFabricPartnerCommunity. We look forward to seeing you later this week!Partner Blog | What's new for Microsoft partners: October 2025 edition
Your voice is instrumental in shaping the future of the Microsoft AI Cloud Partner Program. In our latest quarterly update, we share key enhancements driven by partner feedback, along with expert insights, new skilling resources, and the latest benefits to help you grow, innovate, and lead in the AI era. Continue reading here!The importance of streaming for LLM-powered chat applications
Thanks to the popularity of chat-based interfaces like ChatGPT and GitHub Copilot, users have grown accustomed to getting answers conversationally. As a result, thousands of developers are now deploying chat applications on Azure for their own specialized domains. To help developers understand how to build LLM-powered chat apps, we have open-sourced many chat app templates, like a super simple chat app and the very popular and sophisticated RAG chat app. All our templates support an important feature: streaming. At first glance, streaming might not seem essential. But users have come to expect it from modern chat experiences. Beyond meeting expectations, streaming can dramatically improve the time to first token — letting your frontend display words as soon as they’re generated, instead of making users wait seconds for a complete answer. How to stream from the APIs Most modern LLM APIs and wrapper libraries now support streaming responses — usually through a simple boolean flag or a dedicated streaming method. Let’s look at an example using the official OpenAI Python SDK. The openai package makes it easy to stream responses by passing a stream=True argument: completion_stream = openai_client.chat.completions.create( model="gpt-5-mini", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What does a product manager do?"}, ], stream=True, ) When stream is true, the return type is an iterable, so we can use a for loop to process each of the ChatCompletion chunk objects: for chunk in await completion_stream: content = event.choices[0].delta.content Sending stream from backend to frontend When building a web app, we need a way to stream data from the backend to the browser. A normal HTTP response won’t work here — it sends all the data at once, then closes the connection. Instead, we need a protocol that allows data to arrive progressively. The most common options are: WebSockets: A bidirectional channel where both client and server can send data at any time. Server-sent events: A one-way channel where the server continuously pushes events to the client over HTTP. Readable streams: An HTTP response with a Transfer-encoding header of "chunked", allowing the client to process chunks as they arrive. All of these could potentially be used for a chat app, and I myself have experimented with both server-sent events and readable streams. Behind the scenes, the ChatGPT API actually uses server-sent events, so you'll find code in the openai package for parsing that protocol. However, I now prefer using readable streams for my frontend to backend communication. It's the simplest code setup on both the frontend and backend, and it supports the POST requests that our apps are already sending. The key is to send chunks from the backend in NDJSON (newline-delimited JSON) format and parse them incrementally on the frontend. See my blog post on fetching JSON over streaming HTTP for Python and JavaScript example code. Achieving a word-by-word effect With all of that in place, we now have a frontend that reveals the model’s answer gradually — almost like watching it type in real time. But something still feels off! Despite our frontend receiving chunks of just a few tokens at a time, that UI tends to reveal entire sentences at once. Why does that happen? It turns out the browser is batching repaints. Instead of immediately re-rendering after each DOM update, it waits until it’s more efficient to repaint — a smart optimization in most cases, but not ideal for a streaming text effect. My colleague Steve Steiner explored several techniques to make the browser repaint more frequently. The most effective approach uses window.setTimeout() with a delay of 33 milliseconds for each chunk. While this adds a small overall delay, it stays well within a natural reading pace and produces a smooth, word-by-word reveal. See his PR for implementation details for a React codebase. With that change, our frontend now displays responses at the same granularity as the chat completions API itself — chunk by chunk: Streaming more of the process Many of our sample apps use RAG (Retrieval-Augmented Generation) pipelines that chain together multiple operations — querying data stores (like Azure AI Search), generating embeddings, and finally calling the chat completions API. Naturally, that chain takes longer than a single LLM call, so users may wait several seconds before seeing a response. One way to improve the experience is to stream more of the process itself. Instead of holding back everything until the final answer, the backend can emit progress updates as each step completes — keeping users informed and engaged. For example, your app might display messages like this sequence: Processing your question: "Can you suggest a pizza recipe that incorporates both mushroom and pineapples?" Generated search query "pineapple mushroom pizza recipes" Found three related results from our cookbooks: 1) Mushroom calzone 2) Pineapple ham pizza 3) Mushroom loaf Generating answer to your question... Sure! Here's a recipe for a mushroom pineapple pizza... Adding streamed progress like this makes your app feel responsive and alive, even while the backend is doing complex work. Consider experimenting with progress events in your own chat apps — a few simple updates can greatly improve user trust and engagement. Making it optional After all this talk about streaming, here’s one final recommendation: make streaming optional. Provide a setting in your frontend to disable streaming, and a corresponding non-streaming endpoint in your backend. This flexibility helps both your users and your developers: For users: Some may prefer (or require) a non-streamed experience for accessibility reasons, or simply to receive the full response at once. For developers: There are times when you’ll want to interact with the app programmatically — for example, using curl, requests, or automated tests — and a standard, non-streaming HTTP endpoint makes that much easier. Designing your app to gracefully support both modes ensures it’s inclusive, debuggable, and production-ready. Sample applications We’ve already linked to several of our sample apps that support streaming, but here’s a complete list so you can explore the one that best fits your tech stack: Repository App purpose Backend Frontend azure-search-openai-demo RAG with AI Search Python + Quart React rag-postgres-openai-python RAG with PostgreSQL Python + FastAPI React openai-chat-app-quickstart Simple chat with Azure OpenAI models Python + Quart plain JS openai-chat-backend-fastapi Simple chat with Azure OpenAI models Python + FastAPI plain JS deepseek-python Simple chat with Azure AI Foundry models Python + Quart plain JS Each of these repositories includes streaming support out of the box, so you can inspect real implementation details in both the frontend and backend. They’re a great starting point for learning how to structure your own LLM chat application — or for extending one of the samples to match your specific use case.
📣 Getting Started with AI and MS Copilot - Arabic
👋 مرحبًا بالمعلمين والمعلمات! نأمل أن تكونوا بخير 🌟 هل ترغبون في استكشاف عالم الذكاء الاصطناعي مع Microsoft Copilot؟ ندعوكم لحضور جلسة "مقدمة إلى الذكاء الاصطناعي مع Copilot من مايكروسوفت"، المصمّمة خصيصًا للمعلمين الذين يبدؤون رحلتهم مع Copilot. في هذه الجلسة التفاعلية والعملية، سنقوم معًا برسم "وجهة أحلامنا" باستخدام الذكاء الاصطناعي، ونتعرّف على أساسيات الذكاء الاصطناعي التوليدي، كيفية كتابة تعليمات (Prompts) فعّالة، وأفضل الطرق لتوظيف هذه الأدوات داخل الصف الدراسي. 📌 الجلسة ستكون باللغة العربية، مع أمثلة واقعية، مواد جاهزة، ومساحة مخصصة لطرح الأسئلة والتجربة العملية. 📅 اللقاء سيتم عبر Join the meeting now – اضغط هنا للانضمام في الوقت المحدد.Study Buddy: Learning Data Science and Machine Learning with an AI Sidekick
If you've ever wished for a friendly companion to guide you through the world of data science and machine learning, you're not alone. As part of the "For Beginners" curriculum, I recently built a Study Buddy Agent, an AI-powered assistant designed to help learners explore data science interactively, intuitively, and joyfully. Why a Study Buddy? Learning something new can be overwhelming, especially when you're navigating complex topics like machine learning, statistics, or Python programming. The Study Buddy Agent is here to change that. It brings the curriculum to life by answering questions, offering explanations, and nudging learners toward deeper understanding, all in a conversational format. Think of it as your AI-powered lab partner: always available, never judgmental, and endlessly curious. Built with chatmodes, Powered by Purpose The agent lives inside a .chatmodes file in the https://github.com/microsoft/Data-Science-For-Beginners/blob/main/.github/chatmodes/study-mode.chatmode.md. This file defines how the agent behaves, what tone it uses, and how it interacts with learners. I designed it to be friendly, encouraging, and beginner-first—just like the curriculum itself. It’s not just about answering questions. The Study Buddy is trained to: Reinforce key concepts from the curriculum Offer hints and nudges when learners get stuck Encourage exploration and experimentation Celebrate progress and milestones What’s Under the Hood? The agent uses GitHub Copilot's chatmode, which allows developers to define custom behaviors for AI agents. By aligning the agent’s responses with the curriculum’s learning objectives, we ensure that learners stay on track while enjoying the flexibility of conversational learning. How You Can Use It YouTube Video here: Study Buddy - Data Science AI Sidekick Clone the repo: Head to the https://github.com/microsoft/Data-Science-For-Beginners and clone it locally or use Codespaces. Open the GitHub Copilot Chat, and select Study Buddy: This will activate the Study Buddy. Start chatting: Ask questions, explore topics, and let the agent guide you. What’s Next? This is just the beginning. I’m exploring ways to: Expand the agent to other beginner curriculums (Web Dev, AI, IoT) Integrate feedback loops so learners can shape the agent’s evolution Final Thoughts In my role, I believe learning should be inclusive, empowering, and fun. The Study Buddy Agent is a small step toward that vision, a way to make data science feel less like a mountain and more like a hike with a good friend. Try it out, share your feedback, and let’s keep building tools that make learning magical. Join us on Discord to share your feedback.Build. Secure. Launch Your Private MCP Registry with Azure API Center.
We are thrilled to embrace a new era in the world of MCP registries. As organizations increasingly build and consume MCP servers, the need for a secure, governed, robust and easily discoverable tools catalog has become critical. Today, we are excited to show you how to do just that with MCP Center, a live example demonstrating how Azure API Center (APIC) can serve as a private and enterprise-ready MCP registry. The registry puts your MCPs just one click away for developers, ensuring no setup fuss and a direct path to coding brilliance. Why a private registry? 🤔 Public OSS registries have been instrumental in driving growth and innovation across the MCP ecosystem. But as adoption scales, so does the need for tighter security, governance, and control, this is where private MCP registries step in. This is where Azure API Center steps in. Azure API Center offers a powerful and centralized approach to MCP discovery and governance across diverse teams and services within an organization. Let's delve into the key benefits of leveraging a private MCP registry with Azure API Center. Security and Trust: The Foundation of AI Adoption Review and Verification: Public registries, by their open nature, accept submissions from a wide range of developers. This can introduce risks from tools with limited security practices or even malicious intent. A private registry empowers your organization to thoroughly review and verify every MCP server before it becomes accessible to internal developers or AI agents (like Copilot Studio and AI Foundry). This eliminates the risk of introducing random, potentially vulnerable first or third-party tools into your ecosystem. Reduced Attack Surface: By controlling which MCP servers are accessible, organizations significantly shrink their potential attack surface. When your AI agents interact solely with known and secure internal tools, the likelihood of external attackers exploiting vulnerabilities in unvetted solutions is drastically reduced. Enterprise-Grade Authentication and Authorization: Private registries enable the enforcement of your existing robust enterprise authentication and authorization mechanisms (e.g., OAuth 2) across all MCP servers. Public registries, in contrast, may have varying or less stringent authentication requirements. Enforced AI Gateway Control (Azure API Management): Beyond vetting, a private registry enables organizations to route all MCP server traffic through an AI gateway such as Azure API Management. This ensures that every interaction, whether internal or external, adheres to strict security policies, including centralized authentication, authorization, rate limiting, and threat protection, creating a secure front for your AI services. Governance and Control: Navigating the AI Landscape with Confidence Centralized Oversight and "Single Source of Truth": A private registry provides a centralized "single source of truth" for all AI-related tools and data connections within your organization. This empowers comprehensive oversight of AI initiatives, clearly identifying ownership and accountability for each MCP server. Preventing "Shadow AI": Without a formal registry, individual teams might independently develop or integrate AI tools, leading to "shadow AI" – unmanaged and unmonitored AI deployments that can pose significant risks. A private registry encourages a standardized approach, bringing all AI tools under central governance and visibility. Tailored Tool Development: Organizations can develop and host MCP servers specifically tailored to their unique needs and requirements. This means optimized efficiency and utility, providing specialized tools you won't typically find in broader public registries. Simplified Integration and Accelerated Development: A well-managed private registry simplifies the discovery and integration of internal tools for your AI developers. This significantly accelerates the development and deployment of AI-powered applications, fostering innovation. Good news! Azure API Center can be created for free in any Azure subscription. You can find a detailed guide to help you get started: Inventory and Discover MCP Servers in Your API Center - Azure API Center Get involved 💡 Your remote MCP server can be discoverable on API Center’s MCP Discovery page today! Bring your MCP server and reach Azure customers! These Microsoft partners are shaping the future of the MCP ecosystem by making their remote MCP Servers discoverable via API Center’s MCP Discovery page. Early Partners: Atlassian – Connect to Jira and Confluence for issue tracking and documentation Box – Use Box to securely store, manage and share your photos, videos, and documents in the cloud Neon – Manage and query Neon Postgres databases with natural language Pipedream – Add 1000s of APIs with built-in authentication and 10,000+ tools to your AI assistant or agent - coming soon - Stripe – Payment processing and financial infrastructure tools If partners would like their remote MCP servers to be featured in our Discover Panel, reach out to us here: GitHub/mcp-center and comment under the following GitHub issue: MCP Server Onboarding Request Ready to Get Started? 🚀 Modernize your AI strategy and empower your teams with enhanced discovery, security, and governance of agentic tools. Now's the time to explore creating your own private enterprise MCP registry. Check out MCP Center, a public showcase demonstrating how you can build your own enterprise MCP registry - MCP Center - Build Your Own Enterprise MCP Registry - or go ahead and create your Azure API Center today!AMA: Azure AI Foundry Voice Live API: Build Smarter, Faster Voice Agents
Join us LIVE in the Azure AI Foundry Discord on the 14th October, 2025, 10am PT to learn more about Voice Live API Voice is no longer a novelty, it's the next-gen interface between humans and machines. From automotive assistants to educational tutors, voice-driven agents are reshaping how we interact with technology. But building seamless, real-time voice experiences has often meant stitching together a patchwork of services: STT, GenAI, TTS, avatars, and more. Until now. Introducing Azure AI Foundry Voice Live API Launched into general availability on October 1, 2025, the Azure AI Foundry Voice Live API is a game-changer for developers building voice-enabled agents. It unifies the entire voice stack—speech-to-text, generative AI, text-to-speech, avatars, and conversational enhancements, into a single, streamlined interface. That means: ⚡ Lower latency 🧠 Smarter interactions 🛠️ Simplified development 📈 Scalable deployment Whether you're prototyping a voice bot for customer support or deploying a full-stack assistant in production, Voice Live API accelerates your journey from idea to impact. Ask Me Anything: Deep Dive with the CoreAI Speech Team Join us for a live AMA session where you can engage directly with the engineers behind the API: 🗓️ Date: 14th Oct 2025 🕒 Time: 10am PT 📍 Location: https://aka.ms/foundry/discord See the EVENTS 🎤 Speakers: Qinying Liao, Principal Program Manager, CoreAI Speech Jan Gorgen, Senior Program Manager, CoreAI Speech They’ll walk through real-world use cases, demo the API in action, and answer your toughest questions, from latency optimization to avatar integration. Who Should Attend? This AMA is designed for: AI engineers building multimodal agents Developers integrating voice into enterprise workflows Researchers exploring conversational UX Foundry users looking to scale voice prototypes Why It Matters Voice Live API isn’t just another endpoint, it’s a foundation for building natural, responsive, and production-ready voice agents. With Azure AI Foundry’s orchestration and deployment tools, you can: Skip the glue code Focus on experience design Deploy with confidence across platforms Bring Your Questions Curious about latency benchmarks? Want to know how avatars sync with TTS? Wondering how to integrate with your existing Foundry workflows? This is your chance to ask the team directly.
